2 Commits

Author SHA1 Message Date
Jack
ebd6be09c7 feat(title-chunker): configurable token-count cap with sentence-boundary re-split (#18455)
## Summary

The TitleChunker (both `hierarchy` and `group` methods) had no
token-size ceiling, so a long section without sub-headings became one
giant chunk. This adds a configurable `chunk_token_cap` that guarantees
every text chunk stays within a token budget.
2026-08-18 21:03:51 +08:00
Jack
423c8489b5 fix(chunker): carry overlap-head PDF positions into new chunk (#18148) (#18227)
When `TokenChunker` starts a fresh chunk with an overlap prefix (Go `computeOverlapPrefix` / Python visible-text cut), the previous chunk's **tail PDF coordinates were dropped**. As a result, the overlap head of a PDF chunk is displayed but **not highlighted** — the highlight box is shifted/truncated relative to the displayed span (infiniflow/ragflow#18148).
2026-08-13 22:18:33 +08:00